System and method for the validation and quality assurance of computerized contours of human anatomy

Patent metadata

Field	Value
Publication number	US-9626757-B2
Application number	US-201414454000-A
Country	US
Kind code	B2
Filing date	Aug 7, 2014
Priority date	Aug 8, 2013
Publication date	Apr 18, 2017
Grant date	Apr 18, 2017

Abstract

A system and method for validating the accuracy of delineated contours in computerized imaging using statistical data for generating assessment criterion that define acceptable tolerances for delineated contours, with the statistical data being conditionally updated and/or refined between individual processes for validating delineated contours to thereby adjust the tolerances defined by the assessment criterion in the stored statistical data, such that the stored statistical data is more closely representative of a target population. The present invention may be used to facilitate, as one example, on-line adaptive radiation therapy.

First claim

What is claimed is:

1. A system for validating the accuracy of delineated contours in computerized imaging, with result feedback, comprising:
a storage unit storing one or more assessment metrics, each assessment metric being associated with a selected delineated contour; and
a feedback processor configured to conditionally update and/or refine the stored one or more assessment metrics, by:
receiving a data set associated with one or more computer representations of a delineated anatomy of a patient,
selecting at least one of the one or more assessment metrics stored in the storage unit, wherein the selected at least one assessment metric is associated with the one or more computer representations of the delineated anatomy of the patient, and
applying the selected at least one assessment metric to the one or more computer representations, to generate one or more resultant metrics,

wherein the storage unit further stores metric standards and metric modifiers associated with the selected delineated contour, and
wherein the feedback processor is further configured to:
generate an acceptable tolerance for the one or more resultant metrics, based on the stored metric standards and metric modifiers,
compare the one or more resultant metrics to the generated acceptable tolerance, and
adjust one or both of stored metric standards and metric modifiers, such that a subsequent performance by the feedback processor may use the adjusted stored metric standards and/or metric modifiers.

2. The system of claim 1 , wherein the data set corresponds to a patient receiving adaptive radiation therapy.

3. The system of claim 1 , wherein the data set corresponds to a patient receiving on-line adaptive radiation therapy.

4. The system according to claim 1 , wherein
the feedback processor is further configured to conditionally update and/or refine the stored one or more assessment metrics, by:
conditionally storing one or more of the one or more resultant metrics to the storage unit to update and/or refine the stored one or more assessment metrics.

5. The system according to claim 4 , wherein conditionally storing one or more of the one or more resultant metrics to the storage unit comprises generating a collection of statistical data that is separate from preloaded statistical data in the storage unit.

6. The system according to claim 4 , wherein conditionally storing one or more of the one or more resultant metrics to the storage unit comprises updating and/or refining preloaded statistical data in the storage unit.

7. A system for validating the accuracy of delineated contours in computerized imaging, with result feedback, comprising:
a means for storing one or more assessment metrics, each assessment metric being associated with a selected delineated contour; and
a feedback means for conditionally updating and/or refining the stored one or more assessment metrics, the feedback means comprising:
means for receiving a data set associated with one or more computer representations of a delineated anatomy of a patient,
means for selecting at least one of the one or more assessment metrics stored in the means for storing, wherein the selected at least one assessment metric is associated with the one or more computer representations of the delineated anatomy of the patient, and
means for applying the selected at least one assessment metric to the one or more computer representations to generate one or more resultant metrics,

wherein the means for storing further stores metric standards and metric modifiers associated with the selected delineated contour, and
wherein the feedback means further comprises:
means for generating an acceptable tolerance for the one or more resultant metrics based on the stored metric standards and metric modifiers,
means for comparing the one or more resultant metrics to the generated acceptable tolerance
means for adjusting one or both of the stored metric standards and metric modifiers such that a subsequent performance of the feedback means may use the adjusted stored metric standards and/or metric modifiers.

8. The system of claim 7 , wherein the data set corresponds to a patient receiving adaptive radiation therapy.

9. The system of claim 7 , wherein the data set corresponds to a patient receiving on-line adaptive radiation therapy.

10. The system according to claim 7 , wherein
the feedback means for conditionally updating and/or refining further comprises:
means for conditionally storing one or more of the one or more resultant metrics to the means for storing to update and/or refine one or more assessment metrics.

11. The system according to claim 10 , wherein the means for conditionally storing is configured to store one or more of the one or more resultant metrics to the means for storing by generating a collection of statistical data that is separate from preloaded statistical data in the means for storing.

12. The system according to claim 10 , wherein the means for conditionally storing is configured to store one or more of the one or more resultant metrics to the means for storing by updating and/or refining preloaded statistical data in the means for storing.

13. A process for validating the accuracy of delineated contours in computerized imaging, with result feedback, comprising:
storing one or more assessment metrics in a storage unit, each assessment metric being associated with a selected delineated contour; and
conditionally updating and/or refining the stored one or more assessment metrics with result feedback, by:
receiving a data set associated with one or more computer representations of a delineated anatomy of a patient,
selecting at least one of the one or more assessment metrics stored in the storage unit, wherein the selected at least one assessment metric is associated with the one or more computer representations of the delineated anatomy of the patient, and
applying the selected at least one assessment metric to the one or more computer representations to generate one or more resultant metrics,

wherein the storage unit further stores metric standards and metric modifiers associated with the selected delineated contour, and the method further comprises:
generating an acceptable tolerance for the one or more resultant metrics based on the stored metric standards and metric modifiers,
comparing the one or more resultant metrics to the generated acceptable tolerance, and
adjusting one or both of stored metric standards and metric modifiers such that a subsequent performance of the process may use the adjusted stored metric standards and/or metric modifiers.

14. The process of claim 13 , wherein the data set corresponds to a patient receiving adaptive radiation therapy.

15. The process of claim 13 , wherein the data set corresponds to a patient receiving on-line adaptive radiation therapy.

16. The process according to claim 13 , wherein
conditionally updating and/or refining the stored one or more assessment metrics with result feedback further comprises:
conditionally storing one or more of the one or more resultant metrics to the storing unit to update and/or refine the stored one or more assessment metrics.

17. The process according to claim 16 , wherein conditionally storing one or more of the one or more resultant metrics to the storing unit comprises generating a collection of statistical data that is separate from preloaded statistical data in the storing unit.

18. The process according to claim 16 , wherein conditionally storing one or more of the one or more resultant m

Assignees

• Univ Washington
• Univ Washington

Inventors

• Altman Michael B
• Green Olga
• Kavanaugh James
• Li Hua
• Mutic Sasa
• Wooten Hasani

Classifications

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T2207/30004

  Biomedical image processing · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T2207/10116

  X-ray image · CPC title